Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 34915
    Prev
    Next
    INDEX
    Explanations

    interest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eč
    -0.06
     courage
    -0.06
    #from
    -0.06
     courageous
    -0.06
    .Selenium
    -0.06
     plán
    -0.06
    gun
    -0.06
    Pink
    -0.06
     degree
    -0.06
     배
    -0.06
    POSITIVE LOGITS
    ]));↵↵
    0.07
     갖
    0.07
    mai
    0.07
    dealer
    0.07
     له
    0.07
    ==-
    0.07
    thr
    0.06
    Identifier
    0.06
     امتی
    0.06
    akra
    0.06
    Activations Density 0.051%

    No Known Activations